| { | |
| "leaderboard": [ | |
| { | |
| "model": "GLM-Image", | |
| "link": "https://z.ai/blog/glm-image", | |
| "hf": "https://huggingface.co/zai-org/GLM-Image", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 67.23, | |
| "Style": 84.1, | |
| "World Knowledge": 90.82, | |
| "Attribute-Overall": 69.12, | |
| "Quantity": 76.39, | |
| "Expression": 58.97, | |
| "Material": 74.06, | |
| "Size": 71.53, | |
| "Shape": 48.12, | |
| "Color": 90.0, | |
| "Action-Overall": 60.93, | |
| "Hand": 58.97, | |
| "Full body": 66.3, | |
| "Animal": 65.44, | |
| "Non Contact": 54.08, | |
| "Contact": 52.98, | |
| "State": 67.45, | |
| "Relationship-Overall": 68.15, | |
| "Composition": 67.91, | |
| "Similarity": 67.22, | |
| "Inclusion": 67.93, | |
| "Comparison": 70.31, | |
| "Compound-Overall": 54.38, | |
| "Imagination": 53.06, | |
| "Feature matching": 55.73, | |
| "Grammar-Overall": 64.04, | |
| "Pronoun Reference": 76.84, | |
| "Consistency": 58.33, | |
| "Negation": 55.38, | |
| "Layout-Overall": 72.95, | |
| "2D": 79.78, | |
| "3D": 65.91, | |
| "Logical Reasoning": 31.65, | |
| "Text": 76.15 | |
| }, | |
| { | |
| "model": "Z-Image", | |
| "link": "https://arxiv.org/pdf/2511.22699", | |
| "hf": "https://huggingface.co/Tongyi-MAI/Z-Image", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 78.1, | |
| "Style": 96.8, | |
| "World Knowledge": 94.46, | |
| "Attribute-Overall": 82.48, | |
| "Quantity": 81.25, | |
| "Expression": 69.87, | |
| "Material": 91.98, | |
| "Size": 81.25, | |
| "Shape": 73.12, | |
| "Color": 97.5, | |
| "Action-Overall": 78.9, | |
| "Hand": 74.36, | |
| "Full body": 82.61, | |
| "Animal": 82.35, | |
| "Non Contact": 77.04, | |
| "Contact": 71.43, | |
| "State": 84.43, | |
| "Relationship-Overall": 80.2, | |
| "Composition": 84.8, | |
| "Similarity": 70.0, | |
| "Inclusion": 86.41, | |
| "Comparison": 75.0, | |
| "Compound-Overall": 76.8, | |
| "Imagination": 82.14, | |
| "Feature matching": 71.35, | |
| "Grammar-Overall": 68.98, | |
| "Pronoun Reference": 80.88, | |
| "Consistency": 75.0, | |
| "Negation": 51.54, | |
| "Layout-Overall": 84.89, | |
| "2D": 86.76, | |
| "3D": 82.95, | |
| "Logical Reasoning": 49.08, | |
| "Text": 68.39 | |
| }, | |
| { | |
| "model": "Seedream-4-5-251128", | |
| "link": "https://seed.bytedance.com/en/seedream4_5", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 89.7, | |
| "Style": 99.2, | |
| "World Knowledge": 96.35, | |
| "Attribute-Overall": 91.03, | |
| "Quantity": 87.5, | |
| "Expression": 87.82, | |
| "Material": 97.64, | |
| "Size": 86.81, | |
| "Shape": 85.62, | |
| "Color": 100.0, | |
| "Action-Overall": 88.21, | |
| "Hand": 80.77, | |
| "Full body": 90.22, | |
| "Animal": 91.91, | |
| "Non Contact": 84.69, | |
| "Contact": 86.9, | |
| "State": 93.87, | |
| "Relationship-Overall": 90.61, | |
| "Composition": 92.57, | |
| "Similarity": 85.0, | |
| "Inclusion": 94.57, | |
| "Comparison": 88.28, | |
| "Compound-Overall": 90.08, | |
| "Imagination": 90.05, | |
| "Feature matching": 90.1, | |
| "Grammar-Overall": 84.09, | |
| "Pronoun Reference": 90.07, | |
| "Consistency": 85.65, | |
| "Negation": 76.54, | |
| "Layout-Overall": 92.54, | |
| "2D": 91.54, | |
| "3D": 93.56, | |
| "Logical Reasoning": 73.17, | |
| "Text": 91.67 | |
| }, | |
| { | |
| "model": "LongCat-Image", | |
| "link": "https://arxiv.org/pdf/2512.07584", | |
| "hf": "https://huggingface.co/meituan-longcat/LongCat-Image", | |
| "open_source": true, | |
| "release_date": "2025-12", | |
| "Overall": 73.54, | |
| "Style": 90.7, | |
| "World Knowledge": 89.72, | |
| "Attribute-Overall": 80.88, | |
| "Quantity": 74.31, | |
| "Expression": 79.49, | |
| "Material": 87.74, | |
| "Size": 81.94, | |
| "Shape": 67.5, | |
| "Color": 95.0, | |
| "Action-Overall": 75.48, | |
| "Hand": 64.1, | |
| "Full body": 82.61, | |
| "Animal": 82.35, | |
| "Non Contact": 71.94, | |
| "Contact": 72.02, | |
| "State": 79.25, | |
| "Relationship-Overall": 75.13, | |
| "Composition": 75.34, | |
| "Similarity": 70.56, | |
| "Inclusion": 83.15, | |
| "Comparison": 69.53, | |
| "Compound-Overall": 64.43, | |
| "Imagination": 68.11, | |
| "Feature matching": 60.68, | |
| "Grammar-Overall": 65.78, | |
| "Pronoun Reference": 76.1, | |
| "Consistency": 59.72, | |
| "Negation": 60.0, | |
| "Layout-Overall": 81.34, | |
| "2D": 84.93, | |
| "3D": 77.65, | |
| "Logical Reasoning": 45.87, | |
| "Text": 66.09 | |
| }, | |
| { | |
| "model": "GPT-4o-1.5", | |
| "link": "https://developers.openai.com/api/docs/models/gpt-image-1.5", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-12", | |
| "Overall": 95.77, | |
| "Style": 99.19, | |
| "World Knowledge": 99.2, | |
| "Attribute-Overall": 96.33, | |
| "Quantity": 90.71, | |
| "Expression": 92.31, | |
| "Material": 99.03, | |
| "Size": 97.92, | |
| "Shape": 97.5, | |
| "Color": 100.0, | |
| "Action-Overall": 94.84, | |
| "Hand": 95.51, | |
| "Full body": 95.63, | |
| "Animal": 95.59, | |
| "Non Contact": 91.15, | |
| "Contact": 97.02, | |
| "State": 94.81, | |
| "Relationship-Overall": 96.94, | |
| "Composition": 96.96, | |
| "Similarity": 96.67, | |
| "Inclusion": 99.44, | |
| "Comparison": 93.75, | |
| "Compound-Overall": 98.17, | |
| "Imagination": 98.45, | |
| "Feature matching": 97.87, | |
| "Grammar-Overall": 92.27, | |
| "Pronoun Reference": 97.77, | |
| "Consistency": 90.28, | |
| "Negation": 88.1, | |
| "Layout-Overall": 94.56, | |
| "2D": 93.31, | |
| "3D": 95.83, | |
| "Logical Reasoning": 88.76, | |
| "Text": 97.39 | |
| }, | |
| { | |
| "model": "FLUX.2-klein-base-9b", | |
| "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 79.35, | |
| "Style": 95.8, | |
| "World Knowledge": 91.13, | |
| "Attribute-Overall": 82.16, | |
| "Quantity": 72.92, | |
| "Expression": 76.28, | |
| "Material": 89.15, | |
| "Size": 81.94, | |
| "Shape": 75.62, | |
| "Color": 97.5, | |
| "Action-Overall": 76.78, | |
| "Hand": 71.15, | |
| "Full body": 78.8, | |
| "Animal": 80.15, | |
| "Non Contact": 78.06, | |
| "Contact": 68.26, | |
| "State": 82.55, | |
| "Relationship-Overall": 86.42, | |
| "Composition": 88.85, | |
| "Similarity": 77.78, | |
| "Inclusion": 92.93, | |
| "Comparison": 83.59, | |
| "Compound-Overall": 78.22, | |
| "Imagination": 79.34, | |
| "Feature matching": 77.08, | |
| "Grammar-Overall": 77.51, | |
| "Pronoun Reference": 85.29, | |
| "Consistency": 77.67, | |
| "Negation": 69.23, | |
| "Layout-Overall": 88.62, | |
| "2D": 91.54, | |
| "3D": 85.61, | |
| "Logical Reasoning": 57.34, | |
| "Text": 59.48 | |
| }, | |
| { | |
| "model": "FLUX.2-klein-base-4b", | |
| "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 69.81, | |
| "Style": 94.6, | |
| "World Knowledge": 81.65, | |
| "Attribute-Overall": 78.85, | |
| "Quantity": 65.97, | |
| "Expression": 69.87, | |
| "Material": 84.43, | |
| "Size": 84.03, | |
| "Shape": 72.5, | |
| "Color": 98.33, | |
| "Action-Overall": 69.96, | |
| "Hand": 67.31, | |
| "Full body": 73.37, | |
| "Animal": 75.74, | |
| "Non Contact": 66.84, | |
| "Contact": 60.12, | |
| "State": 75.94, | |
| "Relationship-Overall": 80.58, | |
| "Composition": 84.12, | |
| "Similarity": 74.44, | |
| "Inclusion": 83.7, | |
| "Comparison": 76.56, | |
| "Compound-Overall": 70.62, | |
| "Imagination": 74.49, | |
| "Feature matching": 66.67, | |
| "Grammar-Overall": 73.8, | |
| "Pronoun Reference": 78.31, | |
| "Consistency": 71.3, | |
| "Negation": 71.15, | |
| "Layout-Overall": 86.01, | |
| "2D": 88.6, | |
| "3D": 83.33, | |
| "Logical Reasoning": 50.23, | |
| "Text": 11.78 | |
| }, | |
| { | |
| "model": "FLUX.2-klein-9b", | |
| "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 78.28, | |
| "Style": 97.5, | |
| "World Knowledge": 93.04, | |
| "Attribute-Overall": 84.08, | |
| "Quantity": 75.0, | |
| "Expression": 83.33, | |
| "Material": 89.62, | |
| "Size": 82.64, | |
| "Shape": 76.88, | |
| "Color": 97.5, | |
| "Action-Overall": 80.8, | |
| "Hand": 78.21, | |
| "Full body": 85.33, | |
| "Animal": 83.82, | |
| "Non Contact": 79.08, | |
| "Contact": 73.21, | |
| "State": 84.43, | |
| "Relationship-Overall": 85.15, | |
| "Composition": 88.51, | |
| "Similarity": 72.22, | |
| "Inclusion": 95.65, | |
| "Comparison": 80.47, | |
| "Compound-Overall": 80.03, | |
| "Imagination": 80.87, | |
| "Feature matching": 79.17, | |
| "Grammar-Overall": 73.26, | |
| "Pronoun Reference": 81.99, | |
| "Consistency": 76.39, | |
| "Negation": 61.54, | |
| "Layout-Overall": 88.81, | |
| "2D": 90.81, | |
| "3D": 86.74, | |
| "Logical Reasoning": 57.34, | |
| "Text": 42.82 | |
| }, | |
| { | |
| "model": "FLUX.2-klein-4b", | |
| "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B", | |
| "open_source": true, | |
| "release_date": "2026-1", | |
| "Overall": 72.31, | |
| "Style": 98.4, | |
| "World Knowledge": 86.23, | |
| "Attribute-Overall": 80.45, | |
| "Quantity": 66.67, | |
| "Expression": 73.72, | |
| "Material": 88.21, | |
| "Size": 84.03, | |
| "Shape": 72.5, | |
| "Color": 98.33, | |
| "Action-Overall": 77.09, | |
| "Hand": 69.23, | |
| "Full body": 80.98, | |
| "Animal": 84.56, | |
| "Non Contact": 76.53, | |
| "Contact": 69.64, | |
| "State": 81.13, | |
| "Relationship-Overall": 80.2, | |
| "Composition": 82.43, | |
| "Similarity": 71.67, | |
| "Inclusion": 88.59, | |
| "Comparison": 75.0, | |
| "Compound-Overall": 75.39, | |
| "Imagination": 79.59, | |
| "Feature matching": 71.09, | |
| "Grammar-Overall": 70.86, | |
| "Pronoun Reference": 80.88, | |
| "Consistency": 70.83, | |
| "Negation": 60.38, | |
| "Layout-Overall": 85.07, | |
| "2D": 88.97, | |
| "3D": 81.06, | |
| "Logical Reasoning": 56.19, | |
| "Text": 13.22 | |
| }, | |
| { | |
| "model": "FLUX-2-pro", | |
| "link": "https://docs.bfl.ai/flux_2/flux2_text_to_image", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 88.35, | |
| "Style": 99.29, | |
| "World Knowledge": 96.77, | |
| "Attribute-Overall": 88.79, | |
| "Quantity": 84.72, | |
| "Expression": 75.0, | |
| "Material": 96.23, | |
| "Size": 90.28, | |
| "Shape": 86.25, | |
| "Color": 99.17, | |
| "Action-Overall": 85.5, | |
| "Hand": 76.92, | |
| "Full body": 92.78, | |
| "Animal": 80.88, | |
| "Non Contact": 87.76, | |
| "Contact": 80.36, | |
| "State": 90.57, | |
| "Relationship-Overall": 89.41, | |
| "Composition": 90.88, | |
| "Similarity": 82.22, | |
| "Inclusion": 93.33, | |
| "Comparison": 90.62, | |
| "Compound-Overall": 89.82, | |
| "Imagination": 92.86, | |
| "Feature matching": 86.72, | |
| "Grammar-Overall": 83.15, | |
| "Pronoun Reference": 90.38, | |
| "Consistency": 83.33, | |
| "Negation": 75.77, | |
| "Layout-Overall": 94.13, | |
| "2D": 92.05, | |
| "3D": 96.21, | |
| "Logical Reasoning": 74.31, | |
| "Text": 82.35 | |
| }, | |
| { | |
| "model": "FLUX-2-max", | |
| "link": "https://bfl.ai/models/flux-2-max", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-12", | |
| "Overall": 90.85, | |
| "Style": 99.09, | |
| "World Knowledge": 96.77, | |
| "Attribute-Overall": 90.94, | |
| "Quantity": 90.28, | |
| "Expression": 77.7, | |
| "Material": 97.64, | |
| "Size": 93.06, | |
| "Shape": 86.79, | |
| "Color": 99.17, | |
| "Action-Overall": 87.3, | |
| "Hand": 82.69, | |
| "Full body": 93.3, | |
| "Animal": 86.03, | |
| "Non Contact": 85.2, | |
| "Contact": 84.52, | |
| "State": 90.57, | |
| "Relationship-Overall": 92.22, | |
| "Composition": 94.93, | |
| "Similarity": 84.44, | |
| "Inclusion": 95.56, | |
| "Comparison": 92.19, | |
| "Compound-Overall": 92.27, | |
| "Imagination": 95.15, | |
| "Feature matching": 89.32, | |
| "Grammar-Overall": 86.82, | |
| "Pronoun Reference": 90.77, | |
| "Consistency": 87.5, | |
| "Negation": 82.31, | |
| "Layout-Overall": 95.26, | |
| "2D": 97.35, | |
| "3D": 93.16, | |
| "Logical Reasoning": 78.44, | |
| "Text": 89.38 | |
| }, | |
| { | |
| "model": "FLUX-2-flex", | |
| "link": "https://flux2-flex.com/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 89.35, | |
| "Style": 98.59, | |
| "World Knowledge": 97.1, | |
| "Attribute-Overall": 90.41, | |
| "Quantity": 88.19, | |
| "Expression": 79.05, | |
| "Material": 95.75, | |
| "Size": 92.36, | |
| "Shape": 86.88, | |
| "Color": 100.0, | |
| "Action-Overall": 86.74, | |
| "Hand": 78.21, | |
| "Full body": 90.0, | |
| "Animal": 87.5, | |
| "Non Contact": 83.67, | |
| "Contact": 84.52, | |
| "State": 94.34, | |
| "Relationship-Overall": 92.09, | |
| "Composition": 92.23, | |
| "Similarity": 87.22, | |
| "Inclusion": 96.11, | |
| "Comparison": 92.97, | |
| "Compound-Overall": 90.85, | |
| "Imagination": 92.6, | |
| "Feature matching": 89.06, | |
| "Grammar-Overall": 82.47, | |
| "Pronoun Reference": 90.77, | |
| "Consistency": 79.17, | |
| "Negation": 76.92, | |
| "Layout-Overall": 92.23, | |
| "2D": 90.15, | |
| "3D": 94.32, | |
| "Logical Reasoning": 74.77, | |
| "Text": 88.24 | |
| }, | |
| { | |
| "model": "Z-Image-Turbo", | |
| "link": "https://github.com/Tongyi-MAI/Z-Image", | |
| "hf": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo", | |
| "open_source": true, | |
| "release_date": "2025-11", | |
| "Overall": 71.4, | |
| "Style": 90.0, | |
| "World Knowledge": 92.25, | |
| "Attribute-Overall": 74.57, | |
| "Quantity": 75.0, | |
| "Expression": 58.97, | |
| "Material": 79.25, | |
| "Size": 77.78, | |
| "Shape": 64.38, | |
| "Color": 95.83, | |
| "Action-Overall": 69.3, | |
| "Hand": 62.82, | |
| "Full body": 73.37, | |
| "Animal": 78.68, | |
| "Non Contact": 69.9, | |
| "Contact": 61.31, | |
| "State": 70.28, | |
| "Relationship-Overall": 71.57, | |
| "Composition": 75.68, | |
| "Similarity": 65.0, | |
| "Inclusion": 75.54, | |
| "Comparison": 65.62, | |
| "Compound-Overall": 63.02, | |
| "Imagination": 64.29, | |
| "Feature matching": 61.72, | |
| "Grammar-Overall": 64.57, | |
| "Pronoun Reference": 79.78, | |
| "Consistency": 62.04, | |
| "Negation": 50.77, | |
| "Layout-Overall": 78.36, | |
| "2D": 83.09, | |
| "3D": 73.48, | |
| "Logical Reasoning": 39.68, | |
| "Text": 70.69 | |
| }, | |
| { | |
| "model": "FLUX.2-dev", | |
| "link": "https://github.com/black-forest-labs/flux2", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-dev", | |
| "open_source": true, | |
| "release_date": "2025-11", | |
| "Overall": 84.76, | |
| "Style": 96.6, | |
| "World Knowledge": 95.41, | |
| "Attribute-Overall": 87.39, | |
| "Quantity": 73.61, | |
| "Expression": 73.72, | |
| "Material": 96.23, | |
| "Size": 91.67, | |
| "Shape": 88.12, | |
| "Color": 100.0, | |
| "Action-Overall": 82.22, | |
| "Hand": 74.36, | |
| "Full body": 86.41, | |
| "Animal": 83.82, | |
| "Non Contact": 82.14, | |
| "Contact": 80.95, | |
| "State": 84.43, | |
| "Relationship-Overall": 87.31, | |
| "Composition": 93.24, | |
| "Similarity": 77.78, | |
| "Inclusion": 88.59, | |
| "Comparison": 85.16, | |
| "Compound-Overall": 83.51, | |
| "Imagination": 84.95, | |
| "Feature matching": 82.03, | |
| "Grammar-Overall": 77.41, | |
| "Pronoun Reference": 88.6, | |
| "Consistency": 78.7, | |
| "Negation": 64.62, | |
| "Layout-Overall": 89.55, | |
| "2D": 87.87, | |
| "3D": 91.29, | |
| "Logical Reasoning": 62.84, | |
| "Text": 85.34 | |
| }, | |
| { | |
| "model": "Nano Banana Pro", | |
| "link": "https://nano-banana.pro", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 92.72, | |
| "Style": 99.3, | |
| "World Knowledge": 97.47, | |
| "Attribute-Overall": 91.95, | |
| "Quantity": 90.28, | |
| "Expression": 85.53, | |
| "Material": 97.64, | |
| "Size": 93.75, | |
| "Shape": 85.0, | |
| "Color": 99.17, | |
| "Action-Overall": 91.38, | |
| "Hand": 89.47, | |
| "Full body": 91.11, | |
| "Animal": 90.44, | |
| "Non Contact": 89.8, | |
| "Contact": 94.05, | |
| "State": 92.92, | |
| "Relationship-Overall": 95.43, | |
| "Composition": 96.96, | |
| "Similarity": 96.11, | |
| "Inclusion": 92.39, | |
| "Comparison": 95.31, | |
| "Compound-Overall": 92.91, | |
| "Imagination": 95.15, | |
| "Feature matching": 90.62, | |
| "Grammar-Overall": 89.59, | |
| "Pronoun Reference": 94.49, | |
| "Consistency": 87.96, | |
| "Negation": 85.71, | |
| "Layout-Overall": 93.28, | |
| "2D": 92.65, | |
| "3D": 93.94, | |
| "Logical Reasoning": 80.24, | |
| "Text": 95.65 | |
| }, | |
| { | |
| "model": "wan2.5-t2i-preview", | |
| "link": "https://help.aliyun.com/zh/model-studio/text-to-image-v2-api-reference", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-09", | |
| "Overall": 77.87, | |
| "Style": 92.64, | |
| "World Knowledge": 94.75, | |
| "Attribute-Overall": 81.49, | |
| "Quantity": 75.0, | |
| "Expression": 70.51, | |
| "Material": 91.04, | |
| "Size": 83.09, | |
| "Shape": 78.75, | |
| "Color": 88.33, | |
| "Action-Overall": 74.14, | |
| "Hand": 59.87, | |
| "Full body": 74.46, | |
| "Animal": 77.94, | |
| "Non Contact": 76.04, | |
| "Contact": 72.02, | |
| "State": 81.6, | |
| "Relationship-Overall": 81.98, | |
| "Composition": 85.47, | |
| "Similarity": 74.44, | |
| "Inclusion": 81.52, | |
| "Comparison": 85.16, | |
| "Compound-Overall": 75.45, | |
| "Imagination": 78.09, | |
| "Feature matching": 72.77, | |
| "Grammar-Overall": 72.79, | |
| "Pronoun Reference": 83.7, | |
| "Consistency": 72.69, | |
| "Negation": 61.54, | |
| "Layout-Overall": 76.87, | |
| "2D": 75.74, | |
| "3D": 78.03, | |
| "Logical Reasoning": 55.5, | |
| "Text": 73.12 | |
| }, | |
| { | |
| "model": "Echo-4o", | |
| "link": "https://arxiv.org/pdf/2508.09987", | |
| "hf": "https://huggingface.co/Yejy53/Echo-4o", | |
| "open_source": true, | |
| "release_date": "2025-8", | |
| "Overall": 69.12, | |
| "Style": 92.2, | |
| "World Knowledge": 90.51, | |
| "Attribute-Overall": 79.06, | |
| "Quantity": 70.14, | |
| "Expression": 71.15, | |
| "Material": 84.91, | |
| "Size": 83.33, | |
| "Shape": 68.75, | |
| "Color": 98.33, | |
| "Action-Overall": 68.92, | |
| "Hand": 66.03, | |
| "Full body": 66.3, | |
| "Animal": 77.94, | |
| "Non Contact": 67.86, | |
| "Contact": 59.52, | |
| "State": 75.94, | |
| "Relationship-Overall": 76.52, | |
| "Composition": 81.76, | |
| "Similarity": 70.56, | |
| "Inclusion": 77.72, | |
| "Comparison": 71.09, | |
| "Compound-Overall": 71.78, | |
| "Imagination": 76.79, | |
| "Feature matching": 66.67, | |
| "Grammar-Overall": 75.13, | |
| "Pronoun Reference": 80.51, | |
| "Consistency": 74.54, | |
| "Negation": 70.0, | |
| "Layout-Overall": 82.28, | |
| "2D": 87.13, | |
| "3D": 77.27, | |
| "Logical Reasoning": 44.77, | |
| "Text": 10.06 | |
| }, | |
| { | |
| "model": "UniWorld-V1", | |
| "link": "https://arxiv.org/pdf/2506.03147", | |
| "hf": "https://huggingface.co/LanguageBind/UniWorld-V1", | |
| "open_source": true, | |
| "release_date": "2025-06", | |
| "Overall": 63.11, | |
| "Style": 91.1, | |
| "World Knowledge": 82.91, | |
| "Attribute-Overall": 70.62, | |
| "Quantity": 70.14, | |
| "Expression": 64.74, | |
| "Material": 61.32, | |
| "Size": 72.22, | |
| "Shape": 66.25, | |
| "Color": 99.17, | |
| "Action-Overall": 67.21, | |
| "Hand": 55.13, | |
| "Full body": 72.28, | |
| "Animal": 73.53, | |
| "Non Contact": 63.78, | |
| "Contact": 61.9, | |
| "State": 75.0, | |
| "Relationship-Overall": 67.13, | |
| "Composition": 72.3, | |
| "Similarity": 63.33, | |
| "Inclusion": 64.67, | |
| "Comparison": 64.06, | |
| "Compound-Overall": 54.51, | |
| "Imagination": 58.16, | |
| "Feature matching": 50.78, | |
| "Grammar-Overall": 63.77, | |
| "Pronoun Reference": 74.26, | |
| "Consistency": 64.35, | |
| "Negation": 52.31, | |
| "Layout-Overall": 69.03, | |
| "2D": 73.9, | |
| "3D": 64.02, | |
| "Logical Reasoning": 38.41, | |
| "Text": 26.44 | |
| }, | |
| { | |
| "model": "SD-3.5-Medium", | |
| "link": "https://stability.ai/news/introducing-stable-diffusion-3-5", | |
| "hf": "stabilityai/stable-diffusion-3.5-medium", | |
| "open_source": true, | |
| "release_date": "2024-10", | |
| "Overall": 60.71, | |
| "Style": 89.8, | |
| "World Knowledge": 84.34, | |
| "Attribute-Overall": 66.99, | |
| "Quantity": 59.72, | |
| "Expression": 51.92, | |
| "Material": 67.92, | |
| "Size": 70.83, | |
| "Shape": 63.75, | |
| "Color": 93.33, | |
| "Action-Overall": 60.65, | |
| "Hand": 50.0, | |
| "Full body": 63.04, | |
| "Animal": 69.12, | |
| "Non Contact": 55.61, | |
| "Contact": 52.98, | |
| "State": 71.7, | |
| "Relationship-Overall": 68.78, | |
| "Composition": 74.66, | |
| "Similarity": 61.67, | |
| "Inclusion": 73.37, | |
| "Comparison": 58.59, | |
| "Compound-Overall": 53.35, | |
| "Imagination": 58.16, | |
| "Feature matching": 48.44, | |
| "Grammar-Overall": 59.89, | |
| "Pronoun Reference": 73.53, | |
| "Consistency": 61.57, | |
| "Negation": 44.23, | |
| "Layout-Overall": 70.34, | |
| "2D": 72.06, | |
| "3D": 68.56, | |
| "Logical Reasoning": 37.73, | |
| "Text": 15.23 | |
| }, | |
| { | |
| "model": "Lumina-DiMOO", | |
| "link": "https://synbol.github.io/Lumina-DiMOO/", | |
| "hf": "https://huggingface.co/Alpha-VLLM/Lumina-DiMOO", | |
| "open_source": true, | |
| "release_date": "2025-09", | |
| "Overall": 71.12, | |
| "Style": 89.7, | |
| "World Knowledge": 90.03, | |
| "Attribute-Overall": 81.62, | |
| "Quantity": 69.44, | |
| "Expression": 85.9, | |
| "Material": 81.6, | |
| "Size": 76.39, | |
| "Shape": 80.0, | |
| "Color": 99.17, | |
| "Action-Overall": 73.76, | |
| "Hand": 64.1, | |
| "Full body": 78.8, | |
| "Animal": 75.74, | |
| "Non Contact": 73.98, | |
| "Contact": 64.88, | |
| "State": 82.08, | |
| "Relationship-Overall": 78.43, | |
| "Composition": 83.45, | |
| "Similarity": 74.44, | |
| "Inclusion": 81.52, | |
| "Comparison": 67.97, | |
| "Compound-Overall": 73.32, | |
| "Imagination": 78.83, | |
| "Feature matching": 67.71, | |
| "Grammar-Overall": 70.45, | |
| "Pronoun Reference": 81.99, | |
| "Consistency": 77.78, | |
| "Negation": 52.31, | |
| "Layout-Overall": 82.84, | |
| "2D": 84.93, | |
| "3D": 80.68, | |
| "Logical Reasoning": 45.45, | |
| "Text": 25.57 | |
| }, | |
| { | |
| "model": "MMaDA", | |
| "link": "https://arxiv.org/pdf/2505.15809", | |
| "hf": "https://huggingface.co/Gen-Verse/MMaDA-8B-MixCoT", | |
| "open_source": true, | |
| "release_date": "2025-05", | |
| "Overall": 41.35, | |
| "Style": 82.4, | |
| "World Knowledge": 56.65, | |
| "Attribute-Overall": 48.93, | |
| "Quantity": 45.83, | |
| "Expression": 29.49, | |
| "Material": 54.25, | |
| "Size": 49.31, | |
| "Shape": 44.38, | |
| "Color": 74.17, | |
| "Action-Overall": 37.83, | |
| "Hand": 15.38, | |
| "Full body": 40.22, | |
| "Animal": 52.94, | |
| "Non Contact": 33.16, | |
| "Contact": 25.6, | |
| "State": 56.6, | |
| "Relationship-Overall": 50.25, | |
| "Composition": 55.07, | |
| "Similarity": 57.22, | |
| "Inclusion": 47.28, | |
| "Comparison": 33.59, | |
| "Compound-Overall": 32.35, | |
| "Imagination": 40.56, | |
| "Feature matching": 23.96, | |
| "Grammar-Overall": 55.75, | |
| "Pronoun Reference": 59.19, | |
| "Consistency": 40.28, | |
| "Negation": 65.0, | |
| "Layout-Overall": 30.22, | |
| "2D": 30.15, | |
| "3D": 30.3, | |
| "Logical Reasoning": 17.95, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "OmniGen2", | |
| "link": "https://arxiv.org/pdf/2506.18871", | |
| "hf": "https://huggingface.co/OmniGen2/OmniGen2", | |
| "open_source": true, | |
| "release_date": "2025-06", | |
| "Overall": 63.09, | |
| "Style": 91.9, | |
| "World Knowledge": 86.39, | |
| "Attribute-Overall": 72.12, | |
| "Quantity": 67.36, | |
| "Expression": 73.08, | |
| "Material": 66.04, | |
| "Size": 72.22, | |
| "Shape": 66.25, | |
| "Color": 95.0, | |
| "Action-Overall": 62.83, | |
| "Hand": 55.77, | |
| "Full body": 69.02, | |
| "Animal": 68.38, | |
| "Non Contact": 62.24, | |
| "Contact": 54.17, | |
| "State": 66.51, | |
| "Relationship-Overall": 68.27, | |
| "Composition": 68.24, | |
| "Similarity": 67.78, | |
| "Inclusion": 71.2, | |
| "Comparison": 64.84, | |
| "Compound-Overall": 56.31, | |
| "Imagination": 62.24, | |
| "Feature matching": 50.26, | |
| "Grammar-Overall": 59.89, | |
| "Pronoun Reference": 71.32, | |
| "Consistency": 60.65, | |
| "Negation": 47.31, | |
| "Layout-Overall": 71.64, | |
| "2D": 78.31, | |
| "3D": 64.77, | |
| "Logical Reasoning": 32.5, | |
| "Text": 29.02 | |
| }, | |
| { | |
| "model": "Infinity", | |
| "link": "https://arxiv.org/pdf/2412.04431", | |
| "hf": "https://huggingface.co/FoundationVision/Infinity/tree/main/infinity_8b_512x512_weights", | |
| "open_source": true, | |
| "release_date": "2024-12", | |
| "Overall": 59.81, | |
| "Style": 90.8, | |
| "World Knowledge": 87.97, | |
| "Attribute-Overall": 68.06, | |
| "Quantity": 66.67, | |
| "Expression": 53.21, | |
| "Material": 66.04, | |
| "Size": 77.78, | |
| "Shape": 58.75, | |
| "Color": 93.33, | |
| "Action-Overall": 60.17, | |
| "Hand": 55.13, | |
| "Full body": 65.22, | |
| "Animal": 72.06, | |
| "Non Contact": 58.16, | |
| "Contact": 49.4, | |
| "State": 62.26, | |
| "Relationship-Overall": 69.16, | |
| "Composition": 73.31, | |
| "Similarity": 65.0, | |
| "Inclusion": 67.39, | |
| "Comparison": 67.97, | |
| "Compound-Overall": 51.42, | |
| "Imagination": 55.87, | |
| "Feature matching": 46.88, | |
| "Grammar-Overall": 60.16, | |
| "Pronoun Reference": 73.16, | |
| "Consistency": 65.74, | |
| "Negation": 41.92, | |
| "Layout-Overall": 66.6, | |
| "2D": 71.69, | |
| "3D": 61.36, | |
| "Logical Reasoning": 31.36, | |
| "Text": 12.36 | |
| }, | |
| { | |
| "model": "OneCAT", | |
| "link": "https://arxiv.org/pdf/2509.03498", | |
| "hf": "https://huggingface.co/onecat-ai/OneCAT-3B", | |
| "open_source": true, | |
| "release_date": "2025-09", | |
| "Overall": 58.28, | |
| "Style": 93.3, | |
| "World Knowledge": 82.28, | |
| "Attribute-Overall": 63.46, | |
| "Quantity": 59.42, | |
| "Expression": 58.33, | |
| "Material": 67.45, | |
| "Size": 65.97, | |
| "Shape": 42.5, | |
| "Color": 92.5, | |
| "Action-Overall": 58.56, | |
| "Hand": 35.9, | |
| "Full body": 65.22, | |
| "Animal": 69.12, | |
| "Non Contact": 57.65, | |
| "Contact": 48.81, | |
| "State": 71.23, | |
| "Relationship-Overall": 68.15, | |
| "Composition": 78.04, | |
| "Similarity": 69.44, | |
| "Inclusion": 62.5, | |
| "Comparison": 51.56, | |
| "Compound-Overall": 56.96, | |
| "Imagination": 66.33, | |
| "Feature matching": 47.4, | |
| "Grammar-Overall": 60.83, | |
| "Pronoun Reference": 70.59, | |
| "Consistency": 59.72, | |
| "Negation": 51.54, | |
| "Layout-Overall": 64.74, | |
| "2D": 64.34, | |
| "3D": 65.15, | |
| "Logical Reasoning": 33.41, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "X-Omni", | |
| "link": "https://arxiv.org/pdf/2507.22058", | |
| "hf": "https://huggingface.co/X-Omni/X-Omni-En", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 53.77, | |
| "Style": 72.7, | |
| "World Knowledge": 76.27, | |
| "Attribute-Overall": 60.04, | |
| "Quantity": 63.19, | |
| "Expression": 53.21, | |
| "Material": 58.96, | |
| "Size": 55.56, | |
| "Shape": 53.75, | |
| "Color": 80.83, | |
| "Action-Overall": 54.47, | |
| "Hand": 46.79, | |
| "Full body": 56.52, | |
| "Animal": 62.5, | |
| "Non Contact": 56.63, | |
| "Contact": 42.26, | |
| "State": 60.85, | |
| "Relationship-Overall": 56.6, | |
| "Composition": 61.82, | |
| "Similarity": 56.11, | |
| "Inclusion": 51.09, | |
| "Comparison": 53.12, | |
| "Compound-Overall": 41.75, | |
| "Imagination": 47.45, | |
| "Feature matching": 35.94, | |
| "Grammar-Overall": 59.09, | |
| "Pronoun Reference": 66.91, | |
| "Consistency": 54.17, | |
| "Negation": 55.0, | |
| "Layout-Overall": 62.69, | |
| "2D": 69.49, | |
| "3D": 55.68, | |
| "Logical Reasoning": 29.09, | |
| "Text": 25.0 | |
| }, | |
| { | |
| "model": "FLUX.1-Krea-dev", | |
| "link": "https://www.krea.ai/blog/flux-krea-open-source-release", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 69.88, | |
| "Style": 88.7, | |
| "World Knowledge": 92.56, | |
| "Attribute-Overall": 75.96, | |
| "Quantity": 70.83, | |
| "Expression": 60.9, | |
| "Material": 77.36, | |
| "Size": 79.17, | |
| "Shape": 73.12, | |
| "Color": 99.17, | |
| "Action-Overall": 71.01, | |
| "Hand": 64.74, | |
| "Full body": 70.11, | |
| "Animal": 77.94, | |
| "Non Contact": 72.96, | |
| "Contact": 67.26, | |
| "State": 73.11, | |
| "Relationship-Overall": 73.98, | |
| "Composition": 76.35, | |
| "Similarity": 66.11, | |
| "Inclusion": 77.17, | |
| "Comparison": 75.0, | |
| "Compound-Overall": 64.43, | |
| "Imagination": 67.35, | |
| "Feature matching": 61.46, | |
| "Grammar-Overall": 63.37, | |
| "Pronoun Reference": 77.21, | |
| "Consistency": 67.13, | |
| "Negation": 45.77, | |
| "Layout-Overall": 84.14, | |
| "2D": 86.76, | |
| "3D": 81.44, | |
| "Logical Reasoning": 39.77, | |
| "Text": 44.83 | |
| }, | |
| { | |
| "model": "Hunyuan-Image-2.1", | |
| "link": "https://github.com/Tencent-Hunyuan/HunyuanImage-2.1", | |
| "hf": "https://huggingface.co/spaces/tencent/HunyuanImage-2.1", | |
| "open_source": true, | |
| "release_date": "2025-09", | |
| "Overall": 74.64, | |
| "Style": 90.88, | |
| "World Knowledge": 92.06, | |
| "Attribute-Overall": 79.66, | |
| "Quantity": 86.62, | |
| "Expression": 72.44, | |
| "Material": 78.77, | |
| "Size": 78.47, | |
| "Shape": 68.12, | |
| "Color": 99.17, | |
| "Action-Overall": 77.81, | |
| "Hand": 75.0, | |
| "Full body": 80.98, | |
| "Animal": 82.35, | |
| "Non Contact": 73.71, | |
| "Contact": 72.02, | |
| "State": 82.55, | |
| "Relationship-Overall": 77.54, | |
| "Composition": 78.38, | |
| "Similarity": 70.56, | |
| "Inclusion": 84.78, | |
| "Comparison": 75.0, | |
| "Compound-Overall": 64.82, | |
| "Imagination": 64.54, | |
| "Feature matching": 65.1, | |
| "Grammar-Overall": 62.83, | |
| "Pronoun Reference": 77.94, | |
| "Consistency": 66.2, | |
| "Negation": 44.23, | |
| "Layout-Overall": 84.14, | |
| "2D": 86.76, | |
| "3D": 81.44, | |
| "Logical Reasoning": 46.59, | |
| "Text": 70.11 | |
| }, | |
| { | |
| "model": "BLIP3-o-Next", | |
| "link": "https://arxiv.org/pdf/2505.09568", | |
| "hf": "https://huggingface.co/BLIP3o/BLIP3o-NEXT-SFT-3B", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 65.15, | |
| "Style": 91.0, | |
| "World Knowledge": 86.71, | |
| "Attribute-Overall": 70.94, | |
| "Quantity": 67.36, | |
| "Expression": 73.72, | |
| "Material": 70.28, | |
| "Size": 76.39, | |
| "Shape": 60.62, | |
| "Color": 80.0, | |
| "Action-Overall": 66.83, | |
| "Hand": 57.69, | |
| "Full body": 75.0, | |
| "Animal": 73.53, | |
| "Non Contact": 67.35, | |
| "Contact": 57.74, | |
| "State": 68.87, | |
| "Relationship-Overall": 73.6, | |
| "Composition": 76.01, | |
| "Similarity": 65.0, | |
| "Inclusion": 77.17, | |
| "Comparison": 75.0, | |
| "Compound-Overall": 64.82, | |
| "Imagination": 73.72, | |
| "Feature matching": 55.73, | |
| "Grammar-Overall": 68.05, | |
| "Pronoun Reference": 76.47, | |
| "Consistency": 67.13, | |
| "Negation": 60.0, | |
| "Layout-Overall": 76.31, | |
| "2D": 80.15, | |
| "3D": 72.35, | |
| "Logical Reasoning": 48.64, | |
| "Text": 4.6 | |
| }, | |
| { | |
| "model": "Kolors", | |
| "link": "https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf", | |
| "hf": "https://huggingface.co/Kwai-Kolors/Kolors", | |
| "open_source": true, | |
| "release_date": "2024-7", | |
| "Overall": 46.07, | |
| "Style": 84.4, | |
| "World Knowledge": 77.22, | |
| "Attribute-Overall": 54.17, | |
| "Quantity": 62.5, | |
| "Expression": 33.33, | |
| "Material": 51.89, | |
| "Size": 62.5, | |
| "Shape": 40.62, | |
| "Color": 83.33, | |
| "Action-Overall": 48.0, | |
| "Hand": 42.95, | |
| "Full body": 42.39, | |
| "Animal": 56.62, | |
| "Non Contact": 45.92, | |
| "Contact": 39.88, | |
| "State": 59.43, | |
| "Relationship-Overall": 52.79, | |
| "Composition": 55.41, | |
| "Similarity": 53.89, | |
| "Inclusion": 51.63, | |
| "Comparison": 46.88, | |
| "Compound-Overall": 33.63, | |
| "Imagination": 41.33, | |
| "Feature matching": 25.78, | |
| "Grammar-Overall": 46.66, | |
| "Pronoun Reference": 56.62, | |
| "Consistency": 47.22, | |
| "Negation": 35.77, | |
| "Layout-Overall": 42.91, | |
| "2D": 43.01, | |
| "3D": 42.8, | |
| "Logical Reasoning": 19.77, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Seedream-4.0", | |
| "link": "https://www.volcengine.com/docs/82379/1541523", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-09", | |
| "Overall": 87.35, | |
| "Style": 98.8, | |
| "World Knowledge": 95.41, | |
| "Attribute-Overall": 88.57, | |
| "Quantity": 86.81, | |
| "Expression": 85.9, | |
| "Material": 97.17, | |
| "Size": 84.03, | |
| "Shape": 76.88, | |
| "Color": 100.0, | |
| "Action-Overall": 85.65, | |
| "Hand": 77.56, | |
| "Full body": 87.5, | |
| "Animal": 88.24, | |
| "Non Contact": 80.1, | |
| "Contact": 83.93, | |
| "State": 94.81, | |
| "Relationship-Overall": 87.69, | |
| "Composition": 88.18, | |
| "Similarity": 80.56, | |
| "Inclusion": 94.02, | |
| "Comparison": 87.5, | |
| "Compound-Overall": 86.08, | |
| "Imagination": 88.27, | |
| "Feature matching": 83.85, | |
| "Grammar-Overall": 78.88, | |
| "Pronoun Reference": 84.93, | |
| "Consistency": 79.17, | |
| "Negation": 72.31, | |
| "Layout-Overall": 90.67, | |
| "2D": 90.81, | |
| "3D": 90.53, | |
| "Logical Reasoning": 67.73, | |
| "Text": 93.97 | |
| }, | |
| { | |
| "model": "Imagen-4.0-generate-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-01", | |
| "Overall": 85.84, | |
| "Style": 97.8, | |
| "World Knowledge": 96.36, | |
| "Attribute-Overall": 84.94, | |
| "Quantity": 84.03, | |
| "Expression": 76.92, | |
| "Material": 90.57, | |
| "Size": 89.58, | |
| "Shape": 71.88, | |
| "Color": 98.33, | |
| "Action-Overall": 88.4, | |
| "Hand": 86.54, | |
| "Full body": 94.02, | |
| "Animal": 88.97, | |
| "Non Contact": 85.71, | |
| "Contact": 83.33, | |
| "State": 91.04, | |
| "Relationship-Overall": 89.34, | |
| "Composition": 93.58, | |
| "Similarity": 78.89, | |
| "Inclusion": 95.11, | |
| "Comparison": 85.94, | |
| "Compound-Overall": 85.31, | |
| "Imagination": 90.31, | |
| "Feature matching": 80.21, | |
| "Grammar-Overall": 79.68, | |
| "Pronoun Reference": 86.76, | |
| "Consistency": 77.31, | |
| "Negation": 74.23, | |
| "Layout-Overall": 88.81, | |
| "2D": 88.24, | |
| "3D": 89.39, | |
| "Logical Reasoning": 70.45, | |
| "Text": 77.3 | |
| }, | |
| { | |
| "model": "Runway-Gen4-Image", | |
| "link": "https://docs.dev.runwayml.com/api/#tag/Start-generating/paths/~1v1~1text_to_image/post", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-11", | |
| "Overall": 69.75, | |
| "Style": 93.44, | |
| "World Knowledge": 90.36, | |
| "Attribute-Overall": 74.03, | |
| "Quantity": 72.86, | |
| "Expression": 51.97, | |
| "Material": 89.42, | |
| "Size": 68.06, | |
| "Shape": 65.62, | |
| "Color": 95.0, | |
| "Action-Overall": 70.21, | |
| "Hand": 62.18, | |
| "Full body": 79.35, | |
| "Animal": 82.35, | |
| "Non Contact": 66.15, | |
| "Contact": 60.37, | |
| "State": 71.7, | |
| "Relationship-Overall": 72.56, | |
| "Composition": 74.32, | |
| "Similarity": 62.22, | |
| "Inclusion": 77.84, | |
| "Comparison": 75.78, | |
| "Compound-Overall": 67.76, | |
| "Imagination": 71.65, | |
| "Feature matching": 63.71, | |
| "Grammar-Overall": 70.08, | |
| "Pronoun Reference": 71.21, | |
| "Consistency": 67.59, | |
| "Negation": 71.03, | |
| "Layout-Overall": 76.33, | |
| "2D": 77.61, | |
| "3D": 75.0, | |
| "Logical Reasoning": 49.31, | |
| "Text": 33.43 | |
| }, | |
| { | |
| "model": "Nano Banana", | |
| "link": "https://ainanobanana.io/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-08", | |
| "Overall": 87.29, | |
| "Style": 98.59, | |
| "World Knowledge": 96.2, | |
| "Attribute-Overall": 87.99, | |
| "Quantity": 86.43, | |
| "Expression": 80.77, | |
| "Material": 88.46, | |
| "Size": 95.83, | |
| "Shape": 80.77, | |
| "Color": 98.33, | |
| "Action-Overall": 87.36, | |
| "Hand": 80.13, | |
| "Full body": 93.48, | |
| "Animal": 88.24, | |
| "Non Contact": 83.67, | |
| "Contact": 80.95, | |
| "State": 95.28, | |
| "Relationship-Overall": 92.47, | |
| "Composition": 93.49, | |
| "Similarity": 86.67, | |
| "Inclusion": 94.02, | |
| "Comparison": 96.09, | |
| "Compound-Overall": 88.34, | |
| "Imagination": 90.21, | |
| "Feature matching": 86.46, | |
| "Grammar-Overall": 83.82, | |
| "Pronoun Reference": 90.44, | |
| "Consistency": 83.33, | |
| "Negation": 77.31, | |
| "Layout-Overall": 91.42, | |
| "2D": 93.01, | |
| "3D": 89.77, | |
| "Logical Reasoning": 73.41, | |
| "Text": 73.28 | |
| }, | |
| { | |
| "model": "Stability-AI-stable-image-ultra", | |
| "link": "https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1ultra/post", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-06", | |
| "Overall": 61.96, | |
| "Style": 87.2, | |
| "World Knowledge": 87.18, | |
| "Attribute-Overall": 66.35, | |
| "Quantity": 67.36, | |
| "Expression": 48.08, | |
| "Material": 64.15, | |
| "Size": 69.44, | |
| "Shape": 64.38, | |
| "Color": 91.67, | |
| "Action-Overall": 59.22, | |
| "Hand": 55.77, | |
| "Full body": 58.15, | |
| "Animal": 63.24, | |
| "Non Contact": 61.22, | |
| "Contact": 51.79, | |
| "State": 64.15, | |
| "Relationship-Overall": 69.04, | |
| "Composition": 72.64, | |
| "Similarity": 66.67, | |
| "Inclusion": 70.11, | |
| "Comparison": 62.5, | |
| "Compound-Overall": 54.25, | |
| "Imagination": 60.97, | |
| "Feature matching": 47.4, | |
| "Grammar-Overall": 61.1, | |
| "Pronoun Reference": 78.68, | |
| "Consistency": 58.33, | |
| "Negation": 45.0, | |
| "Layout-Overall": 64.55, | |
| "2D": 67.28, | |
| "3D": 61.74, | |
| "Logical Reasoning": 31.59, | |
| "Text": 39.08 | |
| }, | |
| { | |
| "model": "HiDream_v2L", | |
| "link": "https://hidreamai.com/doc/txt2img/request", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-07", | |
| "Overall": 61.64, | |
| "Style": 87.99, | |
| "World Knowledge": 89.62, | |
| "Attribute-Overall": 64.38, | |
| "Quantity": 65.71, | |
| "Expression": 44.87, | |
| "Material": 57.82, | |
| "Size": 74.26, | |
| "Shape": 59.87, | |
| "Color": 94.92, | |
| "Action-Overall": 59.5, | |
| "Hand": 51.28, | |
| "Full body": 58.56, | |
| "Animal": 67.65, | |
| "Non Contact": 61.98, | |
| "Contact": 51.52, | |
| "State": 65.09, | |
| "Relationship-Overall": 66.62, | |
| "Composition": 71.23, | |
| "Similarity": 64.2, | |
| "Inclusion": 65.93, | |
| "Comparison": 60.32, | |
| "Compound-Overall": 49.28, | |
| "Imagination": 53.75, | |
| "Feature matching": 44.76, | |
| "Grammar-Overall": 58.86, | |
| "Pronoun Reference": 72.35, | |
| "Consistency": 60.0, | |
| "Negation": 44.23, | |
| "Layout-Overall": 69.06, | |
| "2D": 70.41, | |
| "3D": 67.68, | |
| "Logical Reasoning": 26.73, | |
| "Text": 44.31 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Fast-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-01", | |
| "Overall": 77.69, | |
| "Style": 91.9, | |
| "World Knowledge": 95.73, | |
| "Attribute-Overall": 83.01, | |
| "Quantity": 77.08, | |
| "Expression": 75.0, | |
| "Material": 83.02, | |
| "Size": 89.58, | |
| "Shape": 80.0, | |
| "Color": 96.67, | |
| "Action-Overall": 80.23, | |
| "Hand": 76.92, | |
| "Full body": 84.24, | |
| "Animal": 83.09, | |
| "Non Contact": 76.02, | |
| "Contact": 75.6, | |
| "State": 84.91, | |
| "Relationship-Overall": 82.61, | |
| "Composition": 84.12, | |
| "Similarity": 75.56, | |
| "Inclusion": 87.5, | |
| "Comparison": 82.03, | |
| "Compound-Overall": 72.68, | |
| "Imagination": 78.32, | |
| "Feature matching": 66.93, | |
| "Grammar-Overall": 76.87, | |
| "Pronoun Reference": 83.82, | |
| "Consistency": 77.31, | |
| "Negation": 69.23, | |
| "Layout-Overall": 86.75, | |
| "2D": 88.97, | |
| "3D": 84.47, | |
| "Logical Reasoning": 56.82, | |
| "Text": 50.29 | |
| }, | |
| { | |
| "model": "Recraft", | |
| "link": "https://www.recraft.ai/docs#generate-image", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-12", | |
| "Overall": 62.63, | |
| "Style": 87.2, | |
| "World Knowledge": 90.19, | |
| "Attribute-Overall": 68.16, | |
| "Quantity": 68.06, | |
| "Expression": 56.41, | |
| "Material": 70.75, | |
| "Size": 65.97, | |
| "Shape": 57.5, | |
| "Color": 95.83, | |
| "Action-Overall": 60.55, | |
| "Hand": 50.0, | |
| "Full body": 70.65, | |
| "Animal": 76.47, | |
| "Non Contact": 55.61, | |
| "Contact": 48.81, | |
| "State": 63.21, | |
| "Relationship-Overall": 62.56, | |
| "Composition": 64.53, | |
| "Similarity": 59.44, | |
| "Inclusion": 59.24, | |
| "Comparison": 67.19, | |
| "Compound-Overall": 44.85, | |
| "Imagination": 43.37, | |
| "Feature matching": 46.35, | |
| "Grammar-Overall": 63.64, | |
| "Pronoun Reference": 73.16, | |
| "Consistency": 58.33, | |
| "Negation": 58.08, | |
| "Layout-Overall": 57.84, | |
| "2D": 58.82, | |
| "3D": 56.82, | |
| "Logical Reasoning": 29.55, | |
| "Text": 61.78 | |
| }, | |
| { | |
| "model": "FLUX-kontext-max", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 80.0, | |
| "Style": 96.59, | |
| "World Knowledge": 94.19, | |
| "Attribute-Overall": 80.93, | |
| "Quantity": 75.69, | |
| "Expression": 74.32, | |
| "Material": 82.55, | |
| "Size": 86.81, | |
| "Shape": 74.38, | |
| "Color": 94.17, | |
| "Action-Overall": 77.38, | |
| "Hand": 67.95, | |
| "Full body": 83.15, | |
| "Animal": 77.94, | |
| "Non Contact": 77.04, | |
| "Contact": 70.83, | |
| "State": 84.43, | |
| "Relationship-Overall": 85.08, | |
| "Composition": 87.5, | |
| "Similarity": 78.89, | |
| "Inclusion": 90.0, | |
| "Comparison": 81.25, | |
| "Compound-Overall": 78.99, | |
| "Imagination": 83.93, | |
| "Feature matching": 73.96, | |
| "Grammar-Overall": 78.53, | |
| "Pronoun Reference": 84.23, | |
| "Consistency": 78.7, | |
| "Negation": 72.69, | |
| "Layout-Overall": 85.04, | |
| "2D": 86.74, | |
| "3D": 83.33, | |
| "Logical Reasoning": 61.36, | |
| "Text": 61.92 | |
| }, | |
| { | |
| "model": "FLUX-kontext-pro", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 75.84, | |
| "Style": 94.78, | |
| "World Knowledge": 91.61, | |
| "Attribute-Overall": 79.2, | |
| "Quantity": 75.0, | |
| "Expression": 71.62, | |
| "Material": 76.89, | |
| "Size": 84.72, | |
| "Shape": 74.38, | |
| "Color": 97.5, | |
| "Action-Overall": 77.66, | |
| "Hand": 75.0, | |
| "Full body": 79.35, | |
| "Animal": 80.88, | |
| "Non Contact": 71.94, | |
| "Contact": 73.21, | |
| "State": 84.91, | |
| "Relationship-Overall": 79.34, | |
| "Composition": 81.42, | |
| "Similarity": 75.56, | |
| "Inclusion": 83.33, | |
| "Comparison": 74.22, | |
| "Compound-Overall": 72.68, | |
| "Imagination": 75.0, | |
| "Feature matching": 70.31, | |
| "Grammar-Overall": 72.69, | |
| "Pronoun Reference": 84.23, | |
| "Consistency": 76.85, | |
| "Negation": 57.69, | |
| "Layout-Overall": 84.47, | |
| "2D": 85.98, | |
| "3D": 82.95, | |
| "Logical Reasoning": 55.68, | |
| "Text": 50.29 | |
| }, | |
| { | |
| "model": "wan2.2-t2i-plus", | |
| "link": "https://help.aliyun.com/zh/model-studio/text-to-image-v2-api-reference", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-07", | |
| "Overall": 64.82, | |
| "Style": 91.1, | |
| "World Knowledge": 87.34, | |
| "Attribute-Overall": 70.19, | |
| "Quantity": 76.39, | |
| "Expression": 55.77, | |
| "Material": 66.51, | |
| "Size": 71.53, | |
| "Shape": 64.38, | |
| "Color": 94.17, | |
| "Action-Overall": 68.0, | |
| "Hand": 58.33, | |
| "Full body": 75.82, | |
| "Animal": 69.12, | |
| "Non Contact": 68.88, | |
| "Contact": 57.74, | |
| "State": 75.0, | |
| "Relationship-Overall": 73.03, | |
| "Composition": 70.27, | |
| "Similarity": 67.98, | |
| "Inclusion": 77.72, | |
| "Comparison": 79.69, | |
| "Compound-Overall": 61.37, | |
| "Imagination": 66.92, | |
| "Feature matching": 55.73, | |
| "Grammar-Overall": 66.53, | |
| "Pronoun Reference": 73.9, | |
| "Consistency": 56.74, | |
| "Negation": 66.92, | |
| "Layout-Overall": 74.77, | |
| "2D": 77.49, | |
| "3D": 71.97, | |
| "Logical Reasoning": 42.05, | |
| "Text": 13.83 | |
| }, | |
| { | |
| "model": "FLUX.1-dev", | |
| "link": "https://bfl.ai/blog/24-08-01-bfl", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.1-dev", | |
| "open_source": true, | |
| "release_date": "2024-08", | |
| "Overall": 60.97, | |
| "Style": 85.0, | |
| "World Knowledge": 87.5, | |
| "Attribute-Overall": 67.2, | |
| "Quantity": 71.53, | |
| "Expression": 51.92, | |
| "Material": 58.96, | |
| "Size": 74.31, | |
| "Shape": 65.62, | |
| "Color": 90.0, | |
| "Action-Overall": 62.26, | |
| "Hand": 50.0, | |
| "Full body": 69.02, | |
| "Animal": 69.12, | |
| "Non Contact": 60.2, | |
| "Contact": 61.9, | |
| "State": 63.21, | |
| "Relationship-Overall": 66.88, | |
| "Composition": 66.89, | |
| "Similarity": 65.56, | |
| "Inclusion": 72.83, | |
| "Comparison": 60.16, | |
| "Compound-Overall": 45.75, | |
| "Imagination": 46.17, | |
| "Feature matching": 45.31, | |
| "Grammar-Overall": 62.3, | |
| "Pronoun Reference": 76.47, | |
| "Consistency": 61.57, | |
| "Negation": 48.08, | |
| "Layout-Overall": 70.9, | |
| "2D": 74.63, | |
| "3D": 67.05, | |
| "Logical Reasoning": 29.77, | |
| "Text": 32.18 | |
| }, | |
| { | |
| "model": "HiDream-I1-Full", | |
| "link": "https://arxiv.org/pdf/2505.22705", | |
| "hf": "https://huggingface.co/HiDream-ai/HiDream-I1-Full", | |
| "open_source": true, | |
| "release_date": "2025-05", | |
| "Overall": 71.36, | |
| "Style": 92.3, | |
| "World Knowledge": 93.67, | |
| "Attribute-Overall": 73.4, | |
| "Quantity": 73.61, | |
| "Expression": 61.54, | |
| "Material": 72.17, | |
| "Size": 79.17, | |
| "Shape": 62.5, | |
| "Color": 98.33, | |
| "Action-Overall": 72.53, | |
| "Hand": 60.9, | |
| "Full body": 76.09, | |
| "Animal": 74.26, | |
| "Non Contact": 73.98, | |
| "Contact": 68.45, | |
| "State": 78.77, | |
| "Relationship-Overall": 74.24, | |
| "Composition": 76.69, | |
| "Similarity": 67.78, | |
| "Inclusion": 78.26, | |
| "Comparison": 71.88, | |
| "Compound-Overall": 60.31, | |
| "Imagination": 61.99, | |
| "Feature matching": 58.59, | |
| "Grammar-Overall": 62.43, | |
| "Pronoun Reference": 81.62, | |
| "Consistency": 63.89, | |
| "Negation": 41.15, | |
| "Layout-Overall": 77.61, | |
| "2D": 82.72, | |
| "3D": 72.35, | |
| "Logical Reasoning": 40.45, | |
| "Text": 66.67 | |
| }, | |
| { | |
| "model": "Pref-GRPO", | |
| "link": "https://github.com/CodeGoat24/UnifiedReward", | |
| "hf": "https://huggingface.co/CodeGoat24/FLUX.1-dev-PrefGRPO", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 68.41, | |
| "Style": 87.9, | |
| "World Knowledge": 86.08, | |
| "Attribute-Overall": 72.86, | |
| "Quantity": 68.75, | |
| "Expression": 59.62, | |
| "Material": 74.06, | |
| "Size": 76.39, | |
| "Shape": 65.62, | |
| "Color": 98.33, | |
| "Action-Overall": 69.2, | |
| "Hand": 57.69, | |
| "Full body": 72.83, | |
| "Animal": 75.0, | |
| "Non Contact": 70.41, | |
| "Contact": 64.29, | |
| "State": 73.58, | |
| "Relationship-Overall": 76.27, | |
| "Composition": 81.08, | |
| "Similarity": 76.67, | |
| "Inclusion": 75.54, | |
| "Comparison": 65.62, | |
| "Compound-Overall": 62.89, | |
| "Imagination": 66.58, | |
| "Feature matching": 59.11, | |
| "Grammar-Overall": 62.03, | |
| "Pronoun Reference": 77.94, | |
| "Consistency": 66.67, | |
| "Negation": 41.54, | |
| "Layout-Overall": 78.54, | |
| "2D": 83.82, | |
| "3D": 73.11, | |
| "Logical Reasoning": 40.68, | |
| "Text": 47.7 | |
| }, | |
| { | |
| "model": "SD-3.5-Large", | |
| "link": "https://stability.ai/news/introducing-stable-diffusion-3-5", | |
| "hf": "https://huggingface.co/stabilityai/stable-diffusion-3.5-large", | |
| "open_source": true, | |
| "release_date": "2024-10", | |
| "Overall": 62.89, | |
| "Style": 88.6, | |
| "World Knowledge": 89.72, | |
| "Attribute-Overall": 68.8, | |
| "Quantity": 69.44, | |
| "Expression": 51.28, | |
| "Material": 70.28, | |
| "Size": 70.83, | |
| "Shape": 64.38, | |
| "Color": 91.67, | |
| "Action-Overall": 61.98, | |
| "Hand": 57.69, | |
| "Full body": 63.04, | |
| "Animal": 62.5, | |
| "Non Contact": 59.69, | |
| "Contact": 58.93, | |
| "State": 68.4, | |
| "Relationship-Overall": 67.51, | |
| "Composition": 73.99, | |
| "Similarity": 65.0, | |
| "Inclusion": 66.3, | |
| "Comparison": 57.81, | |
| "Compound-Overall": 58.38, | |
| "Imagination": 68.37, | |
| "Feature matching": 48.18, | |
| "Grammar-Overall": 59.89, | |
| "Pronoun Reference": 77.21, | |
| "Consistency": 60.19, | |
| "Negation": 41.54, | |
| "Layout-Overall": 67.72, | |
| "2D": 70.96, | |
| "3D": 64.39, | |
| "Logical Reasoning": 32.05, | |
| "Text": 34.2 | |
| }, | |
| { | |
| "model": "Janus-Pro", | |
| "link": "https://arxiv.org/pdf/2501.17811", | |
| "hf": "https://huggingface.co/deepseek-ai/Janus-Pro-7B", | |
| "open_source": true, | |
| "release_date": "2025-01", | |
| "Overall": 61.36, | |
| "Style": 90.4, | |
| "World Knowledge": 86.55, | |
| "Attribute-Overall": 68.59, | |
| "Quantity": 56.25, | |
| "Expression": 57.69, | |
| "Material": 74.06, | |
| "Size": 73.61, | |
| "Shape": 61.88, | |
| "Color": 90.83, | |
| "Action-Overall": 63.88, | |
| "Hand": 47.44, | |
| "Full body": 65.22, | |
| "Animal": 72.79, | |
| "Non Contact": 60.71, | |
| "Contact": 59.52, | |
| "State": 75.47, | |
| "Relationship-Overall": 69.54, | |
| "Composition": 76.01, | |
| "Similarity": 58.33, | |
| "Inclusion": 73.91, | |
| "Comparison": 64.06, | |
| "Compound-Overall": 60.18, | |
| "Imagination": 67.35, | |
| "Feature matching": 52.86, | |
| "Grammar-Overall": 64.04, | |
| "Pronoun Reference": 76.1, | |
| "Consistency": 64.81, | |
| "Negation": 50.77, | |
| "Layout-Overall": 72.76, | |
| "2D": 74.63, | |
| "3D": 70.83, | |
| "Logical Reasoning": 35.68, | |
| "Text": 2.01 | |
| }, | |
| { | |
| "model": "Show-o2", | |
| "link": "https://arxiv.org/pdf/2506.15564", | |
| "hf": "https://huggingface.co/showlab/show-o2-7B", | |
| "open_source": true, | |
| "release_date": "2025-06", | |
| "Overall": 61.9, | |
| "Style": 87.4, | |
| "World Knowledge": 85.44, | |
| "Attribute-Overall": 69.87, | |
| "Quantity": 59.03, | |
| "Expression": 64.1, | |
| "Material": 70.75, | |
| "Size": 74.31, | |
| "Shape": 61.25, | |
| "Color": 95.0, | |
| "Action-Overall": 69.01, | |
| "Hand": 54.49, | |
| "Full body": 75.0, | |
| "Animal": 75.0, | |
| "Non Contact": 72.45, | |
| "Contact": 50.6, | |
| "State": 82.08, | |
| "Relationship-Overall": 68.78, | |
| "Composition": 76.35, | |
| "Similarity": 60.56, | |
| "Inclusion": 71.2, | |
| "Comparison": 59.38, | |
| "Compound-Overall": 63.79, | |
| "Imagination": 66.84, | |
| "Feature matching": 60.68, | |
| "Grammar-Overall": 60.83, | |
| "Pronoun Reference": 77.57, | |
| "Consistency": 63.43, | |
| "Negation": 41.15, | |
| "Layout-Overall": 73.13, | |
| "2D": 75.37, | |
| "3D": 70.83, | |
| "Logical Reasoning": 39.55, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Bagel", | |
| "link": "https://arxiv.org/pdf/2505.14683", | |
| "hf": "https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT", | |
| "open_source": true, | |
| "release_date": "2025-05", | |
| "Overall": 59.91, | |
| "Style": 90.08, | |
| "World Knowledge": 85.42, | |
| "Attribute-Overall": 67.73, | |
| "Quantity": 56.82, | |
| "Expression": 50.0, | |
| "Material": 73.53, | |
| "Size": 77.94, | |
| "Shape": 59.03, | |
| "Color": 94.44, | |
| "Action-Overall": 62.14, | |
| "Hand": 51.32, | |
| "Full body": 64.88, | |
| "Animal": 67.19, | |
| "Non Contact": 64.53, | |
| "Contact": 56.58, | |
| "State": 66.83, | |
| "Relationship-Overall": 70.64, | |
| "Composition": 77.31, | |
| "Similarity": 68.92, | |
| "Inclusion": 70.0, | |
| "Comparison": 59.17, | |
| "Compound-Overall": 56.86, | |
| "Imagination": 67.5, | |
| "Feature matching": 46.73, | |
| "Grammar-Overall": 65.85, | |
| "Pronoun Reference": 74.17, | |
| "Consistency": 64.44, | |
| "Negation": 58.47, | |
| "Layout-Overall": 76.56, | |
| "2D": 77.73, | |
| "3D": 75.44, | |
| "Logical Reasoning": 23.85, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "BLIP3-o", | |
| "link": "https://arxiv.org/pdf/2505.09568", | |
| "hf": "https://huggingface.co/BLIP3o/BLIP3o-Model-8B", | |
| "open_source": true, | |
| "release_date": "2025-05", | |
| "Overall": 59.57, | |
| "Style": 92.81, | |
| "World Knowledge": 79.97, | |
| "Attribute-Overall": 64.77, | |
| "Quantity": 48.48, | |
| "Expression": 60.26, | |
| "Material": 66.67, | |
| "Size": 76.47, | |
| "Shape": 56.94, | |
| "Color": 83.33, | |
| "Action-Overall": 64.59, | |
| "Hand": 57.24, | |
| "Full body": 71.43, | |
| "Animal": 71.09, | |
| "Non Contact": 63.95, | |
| "Contact": 50.66, | |
| "State": 71.15, | |
| "Relationship-Overall": 65.99, | |
| "Composition": 70.77, | |
| "Similarity": 57.43, | |
| "Inclusion": 66.25, | |
| "Comparison": 65.83, | |
| "Compound-Overall": 54.57, | |
| "Imagination": 64.06, | |
| "Feature matching": 45.54, | |
| "Grammar-Overall": 69.05, | |
| "Pronoun Reference": 81.67, | |
| "Consistency": 61.11, | |
| "Negation": 62.29, | |
| "Layout-Overall": 67.19, | |
| "2D": 69.55, | |
| "3D": 64.91, | |
| "Logical Reasoning": 36.78, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "CogView4", | |
| "link": "https://arxiv.org/pdf/2403.05121", | |
| "hf": "https://huggingface.co/zai-org/CogView4-6B", | |
| "open_source": true, | |
| "release_date": "2024-03", | |
| "Overall": 56.0, | |
| "Style": 80.8, | |
| "World Knowledge": 81.96, | |
| "Attribute-Overall": 63.14, | |
| "Quantity": 70.83, | |
| "Expression": 46.79, | |
| "Material": 55.66, | |
| "Size": 68.75, | |
| "Shape": 58.75, | |
| "Color": 87.5, | |
| "Action-Overall": 59.51, | |
| "Hand": 57.69, | |
| "Full body": 59.78, | |
| "Animal": 69.85, | |
| "Non Contact": 52.55, | |
| "Contact": 53.57, | |
| "State": 65.09, | |
| "Relationship-Overall": 60.91, | |
| "Composition": 58.11, | |
| "Similarity": 60.0, | |
| "Inclusion": 66.3, | |
| "Comparison": 60.94, | |
| "Compound-Overall": 44.97, | |
| "Imagination": 49.23, | |
| "Feature matching": 40.62, | |
| "Grammar-Overall": 54.81, | |
| "Pronoun Reference": 69.49, | |
| "Consistency": 54.17, | |
| "Negation": 40.0, | |
| "Layout-Overall": 69.03, | |
| "2D": 76.84, | |
| "3D": 60.98, | |
| "Logical Reasoning": 27.95, | |
| "Text": 16.95 | |
| }, | |
| { | |
| "model": "Hunyuan-DiT", | |
| "link": "https://arxiv.org/pdf/2405.08748", | |
| "hf": "https://huggingface.co/Tencent-Hunyuan/HunyuanDiT", | |
| "open_source": true, | |
| "release_date": "2024-05", | |
| "Overall": 51.38, | |
| "Style": 94.1, | |
| "World Knowledge": 80.7, | |
| "Attribute-Overall": 62.71, | |
| "Quantity": 67.36, | |
| "Expression": 44.23, | |
| "Material": 71.7, | |
| "Size": 61.81, | |
| "Shape": 47.5, | |
| "Color": 86.67, | |
| "Action-Overall": 49.05, | |
| "Hand": 35.9, | |
| "Full body": 54.89, | |
| "Animal": 54.41, | |
| "Non Contact": 46.94, | |
| "Contact": 35.71, | |
| "State": 62.74, | |
| "Relationship-Overall": 59.64, | |
| "Composition": 60.14, | |
| "Similarity": 64.44, | |
| "Inclusion": 60.33, | |
| "Comparison": 50.78, | |
| "Compound-Overall": 41.62, | |
| "Imagination": 46.68, | |
| "Feature matching": 36.46, | |
| "Grammar-Overall": 55.48, | |
| "Pronoun Reference": 62.87, | |
| "Consistency": 57.87, | |
| "Negation": 45.77, | |
| "Layout-Overall": 44.78, | |
| "2D": 39.34, | |
| "3D": 50.38, | |
| "Logical Reasoning": 24.55, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Janus", | |
| "link": "https://arxiv.org/pdf/2410.13848", | |
| "hf": "https://huggingface.co/deepseek-ai/Janus-1.3B", | |
| "open_source": true, | |
| "release_date": "2024-10", | |
| "Overall": 51.6, | |
| "Style": 90.08, | |
| "World Knowledge": 73.56, | |
| "Attribute-Overall": 55.34, | |
| "Quantity": 35.61, | |
| "Expression": 37.82, | |
| "Material": 60.29, | |
| "Size": 66.18, | |
| "Shape": 48.61, | |
| "Color": 90.74, | |
| "Action-Overall": 50.92, | |
| "Hand": 31.58, | |
| "Full body": 52.38, | |
| "Animal": 62.5, | |
| "Non Contact": 50.0, | |
| "Contact": 39.47, | |
| "State": 65.87, | |
| "Relationship-Overall": 56.54, | |
| "Composition": 58.85, | |
| "Similarity": 52.7, | |
| "Inclusion": 61.25, | |
| "Comparison": 50.0, | |
| "Compound-Overall": 47.1, | |
| "Imagination": 59.38, | |
| "Feature matching": 35.42, | |
| "Grammar-Overall": 61.74, | |
| "Pronoun Reference": 70.0, | |
| "Consistency": 52.22, | |
| "Negation": 60.59, | |
| "Layout-Overall": 52.01, | |
| "2D": 51.82, | |
| "3D": 52.19, | |
| "Logical Reasoning": 28.74, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "Janus-flow", | |
| "link": "https://arxiv.org/pdf/2411.07975", | |
| "hf": "https://huggingface.co/deepseek-ai/JanusFlow-1.3B", | |
| "open_source": true, | |
| "release_date": "2024-11", | |
| "Overall": 47.1, | |
| "Style": 86.34, | |
| "World Knowledge": 62.98, | |
| "Attribute-Overall": 49.2, | |
| "Quantity": 43.18, | |
| "Expression": 30.77, | |
| "Material": 55.39, | |
| "Size": 57.35, | |
| "Shape": 33.33, | |
| "Color": 82.41, | |
| "Action-Overall": 43.57, | |
| "Hand": 22.37, | |
| "Full body": 48.81, | |
| "Animal": 57.81, | |
| "Non Contact": 38.95, | |
| "Contact": 36.84, | |
| "State": 54.81, | |
| "Relationship-Overall": 51.45, | |
| "Composition": 62.69, | |
| "Similarity": 36.49, | |
| "Inclusion": 53.75, | |
| "Comparison": 42.5, | |
| "Compound-Overall": 46.49, | |
| "Imagination": 60.0, | |
| "Feature matching": 33.63, | |
| "Grammar-Overall": 62.8, | |
| "Pronoun Reference": 70.0, | |
| "Consistency": 51.11, | |
| "Negation": 64.41, | |
| "Layout-Overall": 45.76, | |
| "2D": 46.82, | |
| "3D": 44.74, | |
| "Logical Reasoning": 22.41, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "Emu3", | |
| "link": "https://arxiv.org/pdf/2409.18869", | |
| "hf": "https://huggingface.co/BAAI/Emu3-Gen", | |
| "open_source": true, | |
| "release_date": "2024-09", | |
| "Overall": 45.42, | |
| "Style": 87.5, | |
| "World Knowledge": 76.42, | |
| "Attribute-Overall": 50.11, | |
| "Quantity": 42.36, | |
| "Expression": 45.51, | |
| "Material": 52.83, | |
| "Size": 40.28, | |
| "Shape": 46.25, | |
| "Color": 77.5, | |
| "Action-Overall": 40.4, | |
| "Hand": 23.08, | |
| "Full body": 49.46, | |
| "Animal": 54.41, | |
| "Non Contact": 34.69, | |
| "Contact": 29.17, | |
| "State": 50.47, | |
| "Relationship-Overall": 48.6, | |
| "Composition": 55.41, | |
| "Similarity": 44.44, | |
| "Inclusion": 46.74, | |
| "Comparison": 41.41, | |
| "Compound-Overall": 36.21, | |
| "Imagination": 41.33, | |
| "Feature matching": 30.99, | |
| "Grammar-Overall": 50.67, | |
| "Pronoun Reference": 58.09, | |
| "Consistency": 49.07, | |
| "Negation": 44.23, | |
| "Layout-Overall": 43.84, | |
| "2D": 42.28, | |
| "3D": 45.45, | |
| "Logical Reasoning": 19.32, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Playground2.5", | |
| "link": "https://arxiv.org/pdf/2402.17245", | |
| "hf": "https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic", | |
| "open_source": true, | |
| "release_date": "2024-02", | |
| "Overall": 46.02, | |
| "Style": 89.78, | |
| "World Knowledge": 75.8, | |
| "Attribute-Overall": 53.86, | |
| "Quantity": 60.61, | |
| "Expression": 43.59, | |
| "Material": 58.33, | |
| "Size": 45.59, | |
| "Shape": 39.58, | |
| "Color": 81.48, | |
| "Action-Overall": 44.08, | |
| "Hand": 29.61, | |
| "Full body": 54.17, | |
| "Animal": 54.69, | |
| "Non Contact": 37.21, | |
| "Contact": 28.29, | |
| "State": 57.21, | |
| "Relationship-Overall": 53.34, | |
| "Composition": 63.46, | |
| "Similarity": 51.35, | |
| "Inclusion": 48.75, | |
| "Comparison": 40.0, | |
| "Compound-Overall": 35.98, | |
| "Imagination": 44.06, | |
| "Feature matching": 28.27, | |
| "Grammar-Overall": 54.88, | |
| "Pronoun Reference": 62.92, | |
| "Consistency": 51.11, | |
| "Negation": 49.58, | |
| "Layout-Overall": 36.38, | |
| "2D": 33.18, | |
| "3D": 39.47, | |
| "Logical Reasoning": 16.09, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "SDXL", | |
| "link": "https://arxiv.org/pdf/2307.01952", | |
| "hf": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0", | |
| "open_source": true, | |
| "release_date": "2023-07", | |
| "Overall": 40.22, | |
| "Style": 87.45, | |
| "World Knowledge": 72.28, | |
| "Attribute-Overall": 44.66, | |
| "Quantity": 41.67, | |
| "Expression": 25.0, | |
| "Material": 54.9, | |
| "Size": 44.85, | |
| "Shape": 36.11, | |
| "Color": 68.52, | |
| "Action-Overall": 35.1, | |
| "Hand": 19.74, | |
| "Full body": 38.1, | |
| "Animal": 45.31, | |
| "Non Contact": 26.74, | |
| "Contact": 24.34, | |
| "State": 52.4, | |
| "Relationship-Overall": 46.37, | |
| "Composition": 55.38, | |
| "Similarity": 41.22, | |
| "Inclusion": 38.75, | |
| "Comparison": 43.33, | |
| "Compound-Overall": 26.68, | |
| "Imagination": 33.75, | |
| "Feature matching": 19.94, | |
| "Grammar-Overall": 48.48, | |
| "Pronoun Reference": 54.58, | |
| "Consistency": 41.67, | |
| "Negation": 47.46, | |
| "Layout-Overall": 30.8, | |
| "2D": 25.0, | |
| "3D": 36.4, | |
| "Logical Reasoning": 10.34, | |
| "Text": 0.0 | |
| }, | |
| { | |
| "model": "GPT-4o", | |
| "link": "https://platform.openai.com/docs/guides/image-generation", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-03", | |
| "Overall": 92.48, | |
| "Style": 98.98, | |
| "World Knowledge": 98.22, | |
| "Attribute-Overall": 94.01, | |
| "Quantity": 89.29, | |
| "Expression": 96.0, | |
| "Material": 94.66, | |
| "Size": 92.96, | |
| "Shape": 92.5, | |
| "Color": 99.17, | |
| "Action-Overall": 90.78, | |
| "Hand": 88.46, | |
| "Full body": 93.33, | |
| "Animal": 87.88, | |
| "Non Contact": 92.02, | |
| "Contact": 89.16, | |
| "State": 92.31, | |
| "Relationship-Overall": 94.33, | |
| "Composition": 96.58, | |
| "Similarity": 91.11, | |
| "Inclusion": 94.89, | |
| "Comparison": 92.97, | |
| "Compound-Overall": 92.89, | |
| "Imagination": 94.07, | |
| "Feature matching": 91.67, | |
| "Grammar-Overall": 91.21, | |
| "Pronoun Reference": 91.04, | |
| "Consistency": 93.06, | |
| "Negation": 89.75, | |
| "Layout-Overall": 91.35, | |
| "2D": 92.16, | |
| "3D": 90.53, | |
| "Logical Reasoning": 83.79, | |
| "Text": 89.24 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Ultra-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 91.65, | |
| "Style": 99.1, | |
| "World Knowledge": 97.78, | |
| "Attribute-Overall": 92.09, | |
| "Quantity": 94.44, | |
| "Expression": 80.77, | |
| "Material": 95.28, | |
| "Size": 94.44, | |
| "Shape": 88.75, | |
| "Color": 100.0, | |
| "Action-Overall": 92.1, | |
| "Hand": 89.74, | |
| "Full body": 93.41, | |
| "Animal": 93.38, | |
| "Non Contact": 88.78, | |
| "Contact": 87.5, | |
| "State": 98.58, | |
| "Relationship-Overall": 93.53, | |
| "Composition": 96.28, | |
| "Similarity": 87.78, | |
| "Inclusion": 96.2, | |
| "Comparison": 91.41, | |
| "Compound-Overall": 91.37, | |
| "Imagination": 92.86, | |
| "Feature matching": 89.84, | |
| "Grammar-Overall": 87.83, | |
| "Pronoun Reference": 91.91, | |
| "Consistency": 90.28, | |
| "Negation": 81.54, | |
| "Layout-Overall": 92.91, | |
| "2D": 93.75, | |
| "3D": 92.05, | |
| "Logical Reasoning": 80.45, | |
| "Text": 89.37 | |
| }, | |
| { | |
| "model": "Seedream-3.0", | |
| "link": "https://www.byteplus.com/en/product/Seedream", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 78.41, | |
| "Style": 98.19, | |
| "World Knowledge": 94.9, | |
| "Attribute-Overall": 84.62, | |
| "Quantity": 79.02, | |
| "Expression": 81.94, | |
| "Material": 89.62, | |
| "Size": 83.8, | |
| "Shape": 77.22, | |
| "Color": 96.67, | |
| "Action-Overall": 83.14, | |
| "Hand": 75.97, | |
| "Full body": 89.56, | |
| "Animal": 86.03, | |
| "Non Contact": 75.38, | |
| "Contact": 81.93, | |
| "State": 89.1, | |
| "Relationship-Overall": 80.18, | |
| "Composition": 81.57, | |
| "Similarity": 74.16, | |
| "Inclusion": 83.61, | |
| "Comparison": 80.47, | |
| "Compound-Overall": 72.32, | |
| "Imagination": 76.92, | |
| "Feature matching": 67.62, | |
| "Grammar-Overall": 60.3, | |
| "Pronoun Reference": 77.94, | |
| "Consistency": 68.4, | |
| "Negation": 35.14, | |
| "Layout-Overall": 88.74, | |
| "2D": 88.15, | |
| "3D": 89.35, | |
| "Logical Reasoning": 51.83, | |
| "Text": 69.86 | |
| }, | |
| { | |
| "model": "Imagen-3.0-generate-002", | |
| "link": "https://arxiv.org/pdf/2408.07009", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-02", | |
| "Overall": 71.34, | |
| "Style": 89.35, | |
| "World Knowledge": 93.95, | |
| "Attribute-Overall": 77.92, | |
| "Quantity": 71.09, | |
| "Expression": 64.0, | |
| "Material": 85.85, | |
| "Size": 89.78, | |
| "Shape": 64.38, | |
| "Color": 93.28, | |
| "Action-Overall": 78.8, | |
| "Hand": 75.0, | |
| "Full body": 83.89, | |
| "Animal": 80.15, | |
| "Non Contact": 75.65, | |
| "Contact": 71.43, | |
| "State": 85.29, | |
| "Relationship-Overall": 82.75, | |
| "Composition": 83.22, | |
| "Similarity": 76.14, | |
| "Inclusion": 88.27, | |
| "Comparison": 83.06, | |
| "Compound-Overall": 72.81, | |
| "Imagination": 80.36, | |
| "Feature matching": 65.1, | |
| "Grammar-Overall": 69.97, | |
| "Pronoun Reference": 80.88, | |
| "Consistency": 70.28, | |
| "Negation": 57.94, | |
| "Layout-Overall": 80.04, | |
| "2D": 82.35, | |
| "3D": 77.65, | |
| "Logical Reasoning": 45.09, | |
| "Text": 22.7 | |
| }, | |
| { | |
| "model": "DALL-E-3", | |
| "link": "https://openai.com/zh-Hans-CN/index/dall-e-3/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2023-09", | |
| "Overall": 68.85, | |
| "Style": 94.43, | |
| "World Knowledge": 92.64, | |
| "Attribute-Overall": 75.76, | |
| "Quantity": 60.14, | |
| "Expression": 63.16, | |
| "Material": 87.2, | |
| "Size": 84.72, | |
| "Shape": 66.25, | |
| "Color": 91.6, | |
| "Action-Overall": 70.78, | |
| "Hand": 60.78, | |
| "Full body": 76.67, | |
| "Animal": 77.94, | |
| "Non Contact": 68.72, | |
| "Contact": 63.19, | |
| "State": 76.19, | |
| "Relationship-Overall": 78.31, | |
| "Composition": 82.99, | |
| "Similarity": 71.51, | |
| "Inclusion": 85.47, | |
| "Comparison": 66.93, | |
| "Compound-Overall": 71.08, | |
| "Imagination": 78.01, | |
| "Feature matching": 63.95, | |
| "Grammar-Overall": 69.22, | |
| "Pronoun Reference": 76.34, | |
| "Consistency": 72.09, | |
| "Negation": 59.45, | |
| "Layout-Overall": 65.65, | |
| "2D": 54.78, | |
| "3D": 77.25, | |
| "Logical Reasoning": 46.22, | |
| "Text": 24.43 | |
| }, | |
| { | |
| "model": "FLUX-pro-1.1-Ultra", | |
| "link": "https://bfl.ai/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-11", | |
| "Overall": 70.46, | |
| "Style": 90.99, | |
| "World Knowledge": 91.3, | |
| "Attribute-Overall": 76.79, | |
| "Quantity": 72.92, | |
| "Expression": 60.65, | |
| "Material": 79.25, | |
| "Size": 75.0, | |
| "Shape": 78.12, | |
| "Color": 98.33, | |
| "Action-Overall": 71.39, | |
| "Hand": 58.97, | |
| "Full body": 69.02, | |
| "Animal": 76.47, | |
| "Non Contact": 78.06, | |
| "Contact": 65.48, | |
| "State": 77.83, | |
| "Relationship-Overall": 78.05, | |
| "Composition": 81.08, | |
| "Similarity": 74.44, | |
| "Inclusion": 80.98, | |
| "Comparison": 71.88, | |
| "Compound-Overall": 68.17, | |
| "Imagination": 77.3, | |
| "Feature matching": 58.85, | |
| "Grammar-Overall": 68.18, | |
| "Pronoun Reference": 83.46, | |
| "Consistency": 65.74, | |
| "Negation": 54.23, | |
| "Layout-Overall": 80.6, | |
| "2D": 81.25, | |
| "3D": 79.92, | |
| "Logical Reasoning": 41.46, | |
| "Text": 37.64 | |
| }, | |
| { | |
| "model": "Keling-Ketu", | |
| "link": "https://kolors.kuaishou.com/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-04", | |
| "Overall": 65.23, | |
| "Style": 92.25, | |
| "World Knowledge": 87.08, | |
| "Attribute-Overall": 70.81, | |
| "Quantity": 74.29, | |
| "Expression": 56.77, | |
| "Material": 78.67, | |
| "Size": 74.83, | |
| "Shape": 53.75, | |
| "Color": 89.66, | |
| "Action-Overall": 67.81, | |
| "Hand": 53.85, | |
| "Full body": 72.28, | |
| "Animal": 71.32, | |
| "Non Contact": 70.77, | |
| "Contact": 59.28, | |
| "State": 75.94, | |
| "Relationship-Overall": 69.52, | |
| "Composition": 68.14, | |
| "Similarity": 69.27, | |
| "Inclusion": 72.13, | |
| "Comparison": 69.29, | |
| "Compound-Overall": 59.66, | |
| "Imagination": 66.15, | |
| "Feature matching": 53.03, | |
| "Grammar-Overall": 68.99, | |
| "Pronoun Reference": 74.91, | |
| "Consistency": 64.19, | |
| "Negation": 66.8, | |
| "Layout-Overall": 74.57, | |
| "2D": 77.61, | |
| "3D": 71.43, | |
| "Logical Reasoning": 45.6, | |
| "Text": 16.03 | |
| }, | |
| { | |
| "model": "Qwen-Image", | |
| "link": "https://arxiv.org/pdf/2508.02324", | |
| "hf": "https://huggingface.co/Qwen/Qwen-Image", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 78.36, | |
| "Style": 94.7, | |
| "World Knowledge": 94.15, | |
| "Attribute-Overall": 87.93, | |
| "Quantity": 84.03, | |
| "Expression": 85.26, | |
| "Material": 91.98, | |
| "Size": 86.11, | |
| "Shape": 81.88, | |
| "Color": 99.17, | |
| "Action-Overall": 82.6, | |
| "Hand": 78.21, | |
| "Full body": 86.96, | |
| "Animal": 86.76, | |
| "Non Contact": 77.55, | |
| "Contact": 76.79, | |
| "State": 88.68, | |
| "Relationship-Overall": 80.08, | |
| "Composition": 82.09, | |
| "Similarity": 71.11, | |
| "Inclusion": 86.96, | |
| "Comparison": 78.12, | |
| "Compound-Overall": 72.94, | |
| "Imagination": 73.21, | |
| "Feature matching": 72.66, | |
| "Grammar-Overall": 60.96, | |
| "Pronoun Reference": 84.93, | |
| "Consistency": 70.37, | |
| "Negation": 28.08, | |
| "Layout-Overall": 86.57, | |
| "2D": 87.13, | |
| "3D": 85.98, | |
| "Logical Reasoning": 51.59, | |
| "Text": 72.13 | |
| } | |
| ] | |
| } |